CN112016929A - Online payment method and device, electronic equipment and computer storage medium - Google Patents
Online payment method and device, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN112016929A CN112016929A CN202010898825.5A CN202010898825A CN112016929A CN 112016929 A CN112016929 A CN 112016929A CN 202010898825 A CN202010898825 A CN 202010898825A CN 112016929 A CN112016929 A CN 112016929A
- Authority
- CN
- China
- Prior art keywords
- transaction
- current
- current transaction
- value
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4014—Identity check for transactions
Abstract
The application discloses a method and a device for online payment, electronic equipment and a computer storage medium, wherein the method comprises the following steps: when a payment request of the current transaction is received, acquiring transaction data of the current transaction, customer information corresponding to a payment account of the current transaction and historical transaction data of the payment account of the current transaction; inputting transaction data and customer information into a first neural network model trained in advance to obtain a risk pre-evaluation value of the current transaction; inputting the risk estimated value of the current transaction and historical transaction data into a pre-trained second neural network model to obtain a final risk value of the current transaction; if the final risk value is smaller than the preset threshold value, identity information verification is carried out on a target user initiating the current transaction and a question is asked for the target user; if the target user passes the identity information verification and the answer to the question of the target user is correct, responding to the payment request of the current transaction; and if the final risk value is not less than the preset threshold value, closing the current transaction.
Description
Technical Field
The present application relates to the field of online payment technologies, and in particular, to an online payment method and apparatus, an electronic device, and a computer storage medium.
Background
With the continuous development of electronic commerce, not only the number of online transactions is continuously increased, but also the payment mode is simpler and more convenient, so the security of the online transactions is more important.
Nowadays, in order to ensure the security of online transactions and avoid loss to users, the existing main payment method is to verify the password input by users when users pay, or verify the biometric features of users, such as face recognition or fingerprint payment, so as to determine the security of transactions.
However, since the user often makes online payment in public, the online payment password is easily leaked, and the security of the transaction cannot be well determined by verifying the password, so that the user cannot be prevented from being stolen. However, in the case of performing the verification on the biometric feature, the biometric feature of the user may be acquired when the user is not aware of the biometric feature, or the biometric feature may be verified through a photo or a mask, so that the security of the transaction may not be effectively guaranteed. Therefore, the safety of online transaction cannot be well guaranteed by the existing payment mode through a verification mode.
Disclosure of Invention
Based on the defects of the prior art, the application provides an online payment method and device, electronic equipment and a computer storage medium, so as to solve the problem that the security of a transaction cannot be ensured by the existing online payment mode.
In order to achieve the above object, the present application provides the following technical solutions:
a first aspect of the present application provides a method of online payment, comprising:
when a payment request of the current transaction is received, acquiring transaction data of the current transaction, customer information corresponding to a payment account of the current transaction and historical transaction data of the payment account of the current transaction;
inputting the transaction data and the customer information into a first neural network model trained in advance, and calculating a risk pre-evaluation value of the current transaction through the first neural network model;
inputting the risk estimated value of the current transaction and the historical transaction data into a pre-trained second neural network model, and calculating through the second neural network model to obtain a final risk value of the current transaction;
judging whether the final risk value is smaller than a preset threshold value or not;
if the final risk value is smaller than a preset threshold value, performing identity information verification on a target user initiating the current transaction and asking questions of the target user;
if the target user passes the identity information verification and the received question answer of the target user is correct, responding to the payment request of the current transaction;
and if the final risk value is judged to be not smaller than a preset threshold value, closing the current transaction.
Optionally, in the above method for online payment, before the inputting the transaction data and the customer information into a first neural network model trained in advance and calculating a risk pre-estimation value of the current transaction through the first neural network model, the method further includes:
acquiring the transaction time, the transaction place and the transaction equipment identification of the current transaction;
calculating the transaction time and the historical transaction time of the current transaction, the transaction place and the historical transaction place of the current transaction, and the deviation value of the transaction equipment identifier and the historical transaction equipment identifier of the current transaction respectively;
judging whether the sum of the deviation values is larger than a preset deviation value or not;
and if the sum of the deviation values is larger than a preset deviation value, inputting the transaction data and the customer information into a first pre-trained neural network model, and calculating to obtain a risk pre-estimated value of the current transaction through the first neural network model.
Optionally, in the above method for online payment, the calculating deviation values of the transaction time and the historical transaction time of the current transaction, the transaction location and the historical transaction location of the current transaction, and the transaction device identifier and the historical transaction device identifier respectively includes:
calculating the time difference value between the transaction time of the current transaction and each historical transaction time, and taking the minimum time difference value as the deviation value between the transaction time of the current transaction and the historical transaction time;
calculating the distance between the transaction place of the current transaction and each historical transaction place, and taking the minimum distance as the deviation value of the transaction place of the current transaction and the historical transaction place;
judging whether a historical trading equipment identifier consistent with the trading equipment identifier of the current trading exists or not;
if the historical trading equipment identification consistent with the trading equipment identification of the current trading exists, taking a first preset numerical value as a deviation value of the trading equipment identification of the current trading and the historical trading equipment identification;
if the historical trading equipment identification consistent with the trading equipment identification of the current trading does not exist, taking a second preset numerical value as a deviation value of the trading equipment identification of the current trading and the historical trading equipment identification; wherein the first preset value is smaller than the second preset value.
Optionally, in the above method for online payment, after the determining that the final risk value is not less than a preset threshold at the beginning of the year, the method further includes:
sending the transaction data of the current transaction to a client of a transaction manager;
receiving an auditing result fed back by the client of the transaction manager;
if the auditing result indicates that the current transaction is a high-risk transaction, executing the closing of the current transaction;
and if the auditing result indicates that the current transaction is a low-risk transaction, executing the payment request responding to the current transaction.
A second aspect of the present application provides an apparatus for online payment, comprising:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring transaction data of the current transaction, customer information corresponding to a payment account of the current transaction and historical transaction data of the payment account of the current transaction when receiving a payment request of the current transaction;
the first input unit is used for inputting the transaction data and the customer information into a first neural network model trained in advance, and calculating a risk pre-evaluation value of the current transaction through the first neural network model;
the second input unit is used for inputting the risk estimated value of the current transaction and the historical transaction data into a pre-trained second neural network model, and calculating through the second neural network model to obtain a final risk value of the current transaction;
the first judgment unit is used for judging whether the final risk value is smaller than a preset threshold value or not;
the identity authentication unit is used for performing identity information authentication on a target user initiating the current transaction and asking questions to the target user when the first judgment unit judges that the final risk value is smaller than a preset threshold value;
the payment unit is used for responding to the payment request of the current transaction when the target user passes identity information verification and the received question answer of the target user is correct;
and the closing unit is used for closing the current transaction when the first judging unit judges that the final risk value is not less than a preset threshold value.
Optionally, in the above apparatus for online payment, the apparatus further includes:
the second acquisition unit is used for acquiring the transaction time, the transaction place and the transaction equipment identifier of the current transaction;
the deviation value calculating unit is used for respectively calculating deviation values of the transaction time and the historical transaction time of the current transaction, the transaction place and the historical transaction place of the current transaction, and the transaction equipment identifier and the historical transaction equipment identifier of the current transaction;
the second judging unit is used for judging whether the sum of the deviation values is larger than a preset deviation value or not; when the second judgment unit judges that the sum of all deviation values is larger than a preset deviation value, the first input unit inputs the transaction data and the customer information into a first pre-trained neural network model, and a risk pre-estimated value of the current transaction is obtained through calculation of the first neural network model.
Optionally, in the above apparatus for online payment, the offset value calculating unit includes:
the first calculation unit is used for calculating the time difference value between the transaction time of the current transaction and each historical transaction time, and taking the minimum time difference value as the deviation value between the transaction time of the current transaction and the historical transaction time;
the second calculation unit is used for calculating the distance between the transaction place of the current transaction and each historical transaction place, and taking the minimum distance as the deviation value of the transaction place of the current transaction and the historical transaction place;
a third judging unit, configured to judge whether there is a historical transaction device identifier that is consistent with the transaction device identifier of the current transaction;
the first assignment unit is used for taking a first preset numerical value as a deviation value of the transaction equipment identifier of the current transaction and the historical transaction equipment identifier when the third judgment unit judges that the historical transaction equipment identifier consistent with the transaction equipment identifier of the current transaction exists;
the second assignment unit is used for taking a second preset numerical value as a deviation value of the transaction equipment identifier of the current transaction and the historical transaction equipment identifier when the third judgment unit judges that the historical transaction equipment identifier consistent with the transaction equipment identifier of the current transaction does not exist; wherein the first preset value is smaller than the second preset value.
Optionally, in the above apparatus for online payment, the apparatus further includes:
the sending unit is used for sending the transaction data of the current transaction to a client of a transaction manager;
the receiving unit is used for receiving an auditing result fed back by the client of the transaction manager; if the auditing result indicates that the current transaction is a high-risk transaction, the closing unit executes the closing of the current transaction; and if the auditing result indicates that the current transaction is a low-risk transaction, the payment unit executes the payment request responding to the current transaction.
A third aspect of the present application provides an electronic device comprising:
a memory and a processor;
wherein the memory is used for storing programs;
the processor is configured to execute the program, which when executed is particularly configured to implement a method of on-line payment as described in any of the above.
A fourth aspect of the present application provides a computer storage medium storing a computer program which, when executed, is adapted to implement a method of on-line payment as claimed in any one of the preceding claims.
The application provides a method for on-line payment, which comprises the steps of receiving a payment request of a current transaction, acquiring transaction data of the current transaction, customer information corresponding to a payment account of the current transaction and historical transaction data of the payment account of the current transaction, then inputting the transaction data and the customer information into a first neural network model which is trained in advance, calculating to obtain the risk estimated value of the current transaction through a first neural network model, inputting the risk estimated value of the current transaction and historical transaction data into a pre-trained second neural network model, calculating to obtain the final risk value of the current transaction through the second neural network model, therefore, the risk of the current transaction is accurately shortened through the two-stage neural network model, and the current transaction is closed when the final risk value is not less than the preset threshold value, so that the loss of the user is avoided. And when the final risk value is smaller than the preset threshold value, in order to further ensure the safety of the transaction, the identity information of the target user initiating the current transaction is verified and a question is asked to the target user, and when the target user passes the identity information verification and the received question answer of the target user is correct, the payment request of the current transaction is responded, so that the safety of the online transaction can be effectively ensured.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of an online payment method according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart diagram illustrating another method for online payment according to another embodiment of the present application;
FIG. 3 is a flowchart illustrating a method for calculating an offset value according to another embodiment of the present disclosure;
FIG. 4 is a schematic diagram of an apparatus for online payment according to another embodiment of the present application;
fig. 5 is a schematic structural diagram of a deviation calculating unit according to another embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In this application, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiment of the application provides an online payment method, as shown in fig. 1, specifically comprising the following steps:
s101, when a payment request of the current transaction is received, acquiring transaction data of the current transaction, customer information corresponding to a payment account of the current transaction and historical transaction data of the payment account of the current transaction.
The transaction data of the current transaction may specifically include data of transaction time, transaction type, transaction amount, transaction location, payment account information, and the like of the current transaction. The customer information corresponding to the payment account of the current transaction refers to information of an account holder of the payment account of the current transaction, and specifically may include data such as a customer occupation, a customer academic record, and a customer address. The historical transaction data of the payment account of the current transaction mainly refers to historical transaction statistical data of the payment account, such as the number of transactions accumulated by the payment account in the past 30 days, the amount of transactions accumulated in the past 30 days, the number of high-risk transactions in the past 30 days, and the like.
Specifically, when a user initiates payment for a transaction through a client, a payment request of the transaction is sent to a background, and at the moment, transaction data of the current transaction, customer information corresponding to a payment account of the current transaction, and historical transaction data of the payment account of the current transaction are obtained.
And S102, inputting the transaction data and the customer information into a first neural network model trained in advance, and calculating through the first neural network model to obtain a risk pre-evaluation value of the current transaction.
The first neural network model is obtained by training in advance by using transaction data and client information of a plurality of low-risk transactions as positive sample data and using transaction data and client information of a plurality of high-risk transactions as negative sample data. Due to the fact that the specific conditions of the client can remind the user of a normal transaction mode and a consumption level, and transaction data of high-risk transaction and low-risk transaction are obviously different, in the embodiment of the application, the transaction data of the current transaction and client information are processed through the first neural network model, and therefore a risk pre-evaluation value of the current transaction is obtained.
It should be noted that in the embodiment of the present application, a larger risk prediction value indicates a higher risk of the transaction.
S103, inputting the risk estimated value of the current transaction and historical transaction data into a pre-trained second neural network model, and calculating through the second neural network model to obtain the final risk value of the current transaction.
Since the consumption and transaction patterns of a user are generally similar over a period of time, the risk of a transaction can be well predicted from the user's historical transaction data. Therefore, in the embodiment of the application, after the risk pre-evaluation value of the current transaction is obtained, the risk pre-evaluation value of the current transaction and the historical transaction data of the user are input into the pre-trained second neural network model, so that the final risk value of the current transaction is obtained through calculation of the second neural network model, and the historical transaction is further considered, so that the risk value of the transaction can be obtained more accurately. And the two neural network models are used for calculation, so that the mutual interference among different types of data can be effectively avoided, the input result can reflect the influence of the input data on the transaction risk, and a more accurate transaction risk value can be obtained.
In the second neural network model, the risk pre-estimated values and historical transaction data of a plurality of low-risk transactions are used as positive sample data in advance, and the risk pre-estimated values and the historical transaction data of a plurality of high-risk transactions are used as negative sample data for training to obtain the target. It should be noted that, in the case that other data are the same, the larger the risk prediction value of the transaction is, the larger the final risk value of the transaction is calculated by the second neural network model.
Likewise, a greater final risk value for a current transaction indicates a higher risk for the current transaction.
And S104, judging whether the final risk value is smaller than a preset threshold value.
If the final risk value is not smaller than the preset threshold, it indicates that the risk of the current transaction is relatively low, but step S105 is executed at this time in order to further ensure the security of the transaction. If the final risk value is greater than the preset threshold, it indicates that the risk of the current transaction is relatively high, so step S108 is directly performed at this time.
And S105, performing identity information verification on the target user initiating the current transaction and asking questions of the target user.
Specifically, the method may be to perform face recognition or fingerprint recognition on the target user initiating the current transaction, and identify whether the target user is an account issuer of the payment account of the current transaction. And if the target user is identified as the account holder of the payment account of the current transaction, determining that the target user passes the identity information verification. And sending the question to the target user and receiving the answer of the question replied by the user. Wherein the sent question is a preset question for verifying the identity of the target user. The questions can be question-answer questions, selection questions or other forms of giving, and the given questions can be one or more.
S106, judging whether the target user passes the identity information verification or not and whether the received question answer of the target user is correct or not.
If the target user is determined to pass the authentication, and the received answers to the questions of the target user are all verified to be completely correct, step S107 is performed. If it is determined that the target user fails to pass the identity information verification, or the received answer to any question of the target user is incorrect, step S108 is performed.
And S107, responding to the payment request of the current transaction.
It should be noted that, in response to the payment request of the current transaction, i.e. in order to continue to execute the normal payment process, the transaction amount is remitted from the payment account to the collection account.
And S108, closing the current transaction.
Specifically, the initiated current transaction is closed and the payment request for the current transaction is denied. Optionally, after closing the current transaction, an alert message may be sent to the user to inform the user that the current transaction is at risk and has been cancelled.
The method for online payment provided by the embodiment of the application comprises the steps of receiving a payment request of a current transaction, acquiring transaction data of the current transaction, customer information corresponding to a payment account of the current transaction and historical transaction data of the payment account of the current transaction, then inputting the transaction data and the customer information into a first neural network model which is trained in advance, calculating to obtain the risk estimated value of the current transaction through a first neural network model, inputting the risk estimated value of the current transaction and historical transaction data into a pre-trained second neural network model, calculating to obtain the final risk value of the current transaction through the second neural network model, therefore, the risk of the current transaction is accurately shortened through the two-stage neural network model, and the current transaction is closed when the final risk value is not less than the preset threshold value, so that the loss of the user is avoided. And when the final risk value is smaller than the preset threshold value, in order to further ensure the safety of the transaction, the identity information of the target user initiating the current transaction is verified and a question is asked to the target user, and when the target user passes the identity information verification and the received question answer of the target user is correct, the payment request of the current transaction is responded, so that the safety of the online transaction can be effectively ensured.
Another embodiment of the present application provides another online payment method, as shown in fig. 2, which specifically includes the following steps:
s201, when a payment request of the current transaction is received, acquiring transaction data of the current transaction, customer information corresponding to a payment account of the current transaction and historical transaction data of the payment account of the current transaction, wherein the transaction data at least comprises transaction time, transaction place and transaction equipment identification of the current transaction.
It should be noted that, in the embodiment of the present application, the transaction data of the current transaction at least includes the transaction time, the transaction location, and the transaction device identifier of the current transaction, so that when the transaction data is obtained, the transaction time, the transaction location, and the transaction device identifier of the current transaction are obtained. The current transaction may not include the transaction time, the transaction location, and the transaction device identifier of the current transaction, and at this time, the transaction location, and the transaction device identifier of the current transaction need to be additionally obtained.
The specific implementation of step S201 may refer to step S101 in the above method embodiment, and is not described herein again.
S202, calculating deviation values of the transaction time and the historical transaction time of the current transaction, the transaction place and the historical transaction place of the current transaction, and the transaction equipment identifier and the historical transaction equipment identifier of the current transaction respectively.
The historical transaction time refers to the time of the historical transaction of the payment account, and specifically may be an accurate time point, and may be a time period, and the time of the historical transaction with the occurrence frequency meeting the preset frequency is generally set as the historical transaction time for calculating the deviation value, rather than setting the time of all the historical transactions as the historical transaction time for calculating the deviation value. The historical transaction location refers to a location of the historical transaction of the payment account, and specifically may be coordinates of the location, or may be an area, and also, only the location of the historical transaction whose occurrence frequency meets the preset frequency is usually set as the historical transaction location for calculating the deviation value. The transaction device identifier is an identifier of a device used for performing historical transactions of the payment account, and only the device identifier of the historical transactions with the occurrence frequency meeting the preset frequency is set as the historical transaction device identifier for calculating the deviation value.
In the embodiment of the application, the transaction time, the transaction place and the transaction equipment identifier of the current transaction are compared with the transaction time, the transaction place and the transaction equipment identifier of the historical transaction, so that the risk of the transaction is preliminarily judged.
Specifically, the transaction time, the transaction location and the transaction equipment identifier of the current transaction are extracted from the transaction data, and then a deviation value between the transaction time and the historical transaction time of the current transaction, a deviation value between the transaction location and the historical transaction location of the current transaction and a deviation value between the transaction equipment identifier of the current transaction and the historical transaction equipment identifier are calculated.
Optionally, another embodiment of the present application provides a specific implementation manner of step S202, as shown in fig. 3, specifically including the following steps:
s301, calculating time difference values of the current transaction time and the historical transaction times, and taking the minimum time difference value as a deviation value of the transaction time of the current transaction and the historical transaction time.
It should be noted that, in the embodiment of the present application, the transaction time refers to a certain time point or time period in a day. Since the historical transaction time is usually plural, the time difference between the current transaction time and each historical transaction time needs to be calculated. Because the normal transaction time of the user is at the historical transaction time point or very close to a certain historical transaction time, when high-risk behaviors such as fraud, embezzlement and the like occur, the probability that a large difference exists between the transaction time and the historical transaction time of the user is very high. Therefore, the minimum time difference value in the application is used as a deviation value between the transaction time of the current transaction and the historical transaction time. Therefore, the higher the transaction risk is, the larger the deviation value between the transaction time of the current transaction and the historical transaction time is.
S302, calculating the distance between the transaction place of the current transaction and each historical transaction place, and taking the minimum distance as the deviation value between the transaction place of the current transaction and the historical transaction place.
Also, users typically only deal in places where they live for long periods of time and places where they often go, or in the vicinity of such places, so when users do not deal in historical trading places, there may be a greater risk of dealing. And, the farther the current transaction location is from the historical transaction location, the greater the risk. Therefore, in the embodiment of the present application, the distance between the transaction location of the current transaction and each historical transaction location is calculated, and the minimum distance is used as the deviation value between the transaction location of the current transaction and the historical transaction location.
S303, judging whether a historical trading device identification consistent with the trading device identification of the current trading exists.
Similarly, since the user usually only uses his/her own collection or computer or other common devices to perform transactions, if the user uses other devices not belonging to the historical transaction device to perform transactions, there may be a greater risk, and thus, by determining whether there is a historical transaction device identifier that is consistent with the transaction device identifier of the current transaction, it is determined whether the current transaction device is the historical transaction device.
If it is determined that there is a historical transaction device identifier that is consistent with the transaction device identifier of the current transaction, step S304 is executed. If it is determined that there is no historical transaction device identifier that matches the transaction device identifier of the current transaction, step S305 is executed.
S304, taking the first preset value as a deviation value between the transaction equipment identifier of the current transaction and the historical transaction equipment identifier.
S305, taking a second preset value as a deviation value of the transaction equipment identifier of the current transaction and the historical transaction equipment identifier, wherein the first preset value is smaller than the second preset value.
Because the numerical value cannot be obtained through calculation of the trading device identification directly, the value is assigned in an assignment mode, and when the trading device of the current trading does not belong to the historical trading device, a larger numerical value is given, so that the current trading has higher risk. When the transaction equipment of the current transaction does not belong to the historical transaction equipment, a smaller numerical value is given, the specific assignment value can be 0, namely the first preset value can be 0, so that the current transaction has no risk or has higher risk on the factor of the transaction equipment.
It should be noted that, since the three deviation values are calculated independently, the execution sequence of the steps 301 to S306 in the embodiment of the present application is only one optional manner, and may be executed in another sequence. In addition, in the embodiment of the present application, the three deviation values, that is, one example of the three deviation values, may also be calculated in other manners, and as long as the three obtained deviation values are obtained, the calculation manners that can reflect the current transaction risk all belong to the protection scope of the present application.
S203, judging whether the sum of the deviation values is larger than a preset deviation value.
In the embodiment of the application, the larger the three deviation values are, the higher the risk of the current transaction is, so that whether the current transaction is a high-risk transaction or a low-risk transaction is determined by judging whether the sum of the three deviation values is greater than the preset deviation value. If the sum of the deviation values is greater than the preset deviation value, it indicates that the risk of the current transaction is high, so step S204 is executed at this time. If the sum of the deviation values is not greater than the preset deviation value, it indicates that the current transaction is similar to the user' S daily transaction and belongs to a daily transaction behavior, so the execution may execute step S212.
It should be noted that the preset deviation value is usually set to be relatively small, so that when any one of the three deviation values is relatively large, the subsequent steps need to be performed to ensure the safety of payment.
And S204, inputting the transaction data and the customer information into a first neural network model trained in advance, and calculating through the first neural network model to obtain a risk pre-evaluation value of the current transaction.
It should be noted that, the specific implementation of step S204 may refer to step S102 in the foregoing method embodiment, and details are not repeated here.
S205, inputting the risk estimated value of the current transaction and historical transaction data into a pre-trained second neural network model, and calculating through the second neural network model to obtain the final risk value of the current transaction.
It should be noted that, the specific implementation of step S205 may refer to step S105 in the foregoing method embodiment, and details are not repeated here.
And S206, judging whether the final risk value is smaller than a preset threshold value.
If the final risk value is smaller than the preset threshold value, it indicates that the risk of the current transaction is low, and if the security of the transaction is further ensured, step S207 is executed. If the final risk value is not smaller than the preset threshold value, the risk of the current transaction is high, and may exceed the tolerance range of the user or even the bank, so in order to ensure security, in the embodiment of the present application, the verification is further performed manually, and step S209 is executed at this time.
And S207, verifying identity information of the target user initiating the current transaction and asking questions of the target user.
Wherein step S208 is executed after step S207 is executed.
It should be noted that, the specific implementation of step S207 may refer to step S105 in the foregoing method embodiment, and details are not repeated here.
S208, judging whether the target user passes the identity authentication and whether the received answer of the target user is correct.
If the target user is determined to pass the authentication and the received answer of the target user is correct, step S212 is executed, and if the target user is determined not to pass the authentication or the received answer of the target user is incorrect, step S213 is executed.
And S209, transmitting the transaction data of the current transaction to the client of the transaction manager.
Specifically, the current transaction data is sent to a client of a transaction manager, and the transaction manager performs auditing and feeds back an auditing result through the client after auditing. Step S210 is performed after step S209 is performed.
And S210, receiving an auditing result fed back by the client of the transaction manager.
Wherein. After step S210 is performed, step S211 is performed.
S211, judging whether the auditing result indicates that the current transaction is a high-risk transaction.
If the audit result indicates that the current transaction is a high risk transaction, executing step S213; if the audit result indicates that the current transaction is a low risk transaction, step S212 is executed.
S212, responding to the payment request of the current transaction.
It should be noted that, in the specific implementation of step S212, reference may be made to step S107 in the foregoing method embodiment, and details are not described here again.
And S213, closing the current transaction.
It should be noted that, in the specific implementation of step S213, reference may be made to step S108 in the foregoing method embodiment, and details are not described here again.
Another embodiment of the present application provides an apparatus for online payment, as shown in fig. 4, specifically including the following units:
the first obtaining unit 401 is configured to obtain transaction data of a current transaction, customer information corresponding to a payment account of the current transaction, and historical transaction data of the payment account of the current transaction when a payment request of the current transaction is received.
A first input unit 402, configured to input the transaction data and the customer information into a first neural network model trained in advance, and calculate a risk pre-estimated value of the current transaction through the first neural network model.
The second input unit 403 is configured to input the risk pre-estimated value of the current transaction and the historical transaction data into a pre-trained second neural network model, and obtain a final risk value of the current transaction through calculation of the second neural network model.
A first determining unit 404, configured to determine whether the final risk value is smaller than a preset threshold.
And an identity authentication unit 405, configured to, when the first determining unit 404 determines that the final risk value is smaller than the preset threshold, perform identity information authentication on the target user initiating the current transaction and ask a question to the target user.
And a payment unit 406, configured to respond to the payment request of the current transaction when the target user is authenticated by the identity information and the received answer to the question of the target user is correct.
A closing unit 407, configured to close the current transaction when the first determining unit 404 determines that the final risk value is not less than the preset threshold.
Optionally, in an apparatus for online payment provided in another embodiment of the present application, the apparatus further includes the following unit:
and the second acquisition unit is used for acquiring the transaction time, the transaction place and the transaction equipment identifier of the current transaction.
And the deviation value calculating unit is used for calculating deviation values of the transaction time and the historical transaction time of the current transaction, the transaction place and the historical transaction place of the current transaction, and the transaction equipment identifier and the historical transaction equipment identifier of the current transaction respectively.
The second judging unit is used for judging whether the sum of the deviation values is larger than the preset deviation value or not; when the second judging unit judges that the sum of the deviation values is larger than the preset deviation value, the first input unit 402 inputs the transaction data and the customer information into a first neural network model trained in advance, and a risk pre-estimated value of the current transaction is obtained through calculation of the first neural network model.
Optionally, in an apparatus for online payment provided in another embodiment of the present application, as shown in fig. 5, the deviation value calculating unit specifically includes the following units:
the first calculating unit 501 is configured to calculate time difference values between the transaction time of the current transaction and each historical transaction time, and use the minimum time difference value as a deviation value between the transaction time of the current transaction and the historical transaction time.
The second calculating unit 502 is configured to calculate distances between the transaction location of the current transaction and each historical transaction location, and use the minimum distance as a deviation value between the transaction location of the current transaction and the historical transaction location.
A third determining unit 503, configured to determine whether there is a historical transaction device identifier that is consistent with the transaction device identifier of the current transaction.
The first assigning unit 504 is configured to, when the third determining unit 503 determines that there is a historical transaction device identifier that is consistent with the transaction device identifier of the current transaction, use the first preset value as a deviation value between the transaction device identifier of the current transaction and the historical transaction device identifier.
And the second assigning unit 505 is configured to, when the third determining unit 503 determines that there is no historical transaction device identifier that is consistent with the transaction device identifier of the current transaction, use a second preset value as a deviation value between the transaction device identifier of the current transaction and the historical transaction device identifier.
Wherein the first preset value is smaller than the second preset value.
Optionally, in an apparatus for online payment provided in another embodiment of the present application, the apparatus further includes:
and the sending unit is used for sending the transaction data of the current transaction to the client of the transaction manager.
And the receiving unit is used for receiving the auditing result fed back by the client of the transaction manager.
If the auditing result indicates that the current transaction is a high-risk transaction, the closing unit executes closing of the current transaction; and if the auditing result indicates that the current transaction is a low-risk transaction, the payment unit executes a payment request responding to the current transaction.
It should be noted that, for the specific working processes of the units disclosed in the foregoing embodiments, reference may be made to the implementation of the corresponding steps in the foregoing method embodiments, and details are not described here again.
Another embodiment of the present application provides an electronic device, as shown in fig. 6, including:
a memory 601 and a processor 602.
The memory 601 is used for storing programs. The processor 602 is used to execute programs stored in the memory 601. The program, when executed, is particularly adapted to implement a method of online payment as provided by any of the method embodiments described above.
A fourth aspect of the present application provides a computer storage medium storing a computer program which, when executed, is adapted to implement a method of online payment as provided in any one of the method embodiments above.
Computer storage media, including permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory computer readable media (transmyedia) such as modulated data signals and carrier waves.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of online payment, comprising:
when a payment request of the current transaction is received, acquiring transaction data of the current transaction, customer information corresponding to a payment account of the current transaction and historical transaction data of the payment account of the current transaction;
inputting the transaction data and the customer information into a first neural network model trained in advance, and calculating a risk pre-evaluation value of the current transaction through the first neural network model;
inputting the risk estimated value of the current transaction and the historical transaction data into a pre-trained second neural network model, and calculating through the second neural network model to obtain a final risk value of the current transaction;
judging whether the final risk value is smaller than a preset threshold value or not;
if the final risk value is smaller than a preset threshold value, performing identity information verification on a target user initiating the current transaction and asking questions of the target user;
if the target user passes the identity information verification and the received question answer of the target user is correct, responding to the payment request of the current transaction;
and if the final risk value is judged to be not smaller than a preset threshold value, closing the current transaction.
2. The method of claim 1, wherein said inputting said transaction data and said customer information into a first neural network model trained in advance, before calculating a risk pre-estimate for said current transaction using said first neural network model, further comprises:
acquiring the transaction time, the transaction place and the transaction equipment identification of the current transaction;
calculating the transaction time and the historical transaction time of the current transaction, the transaction place and the historical transaction place of the current transaction, and the deviation value of the transaction equipment identifier and the historical transaction equipment identifier of the current transaction respectively;
judging whether the sum of the deviation values is larger than a preset deviation value or not;
and if the sum of the deviation values is larger than a preset deviation value, inputting the transaction data and the customer information into a first pre-trained neural network model, and calculating to obtain a risk pre-estimated value of the current transaction through the first neural network model.
3. The method of claim 2, wherein calculating the deviation values of the transaction time and the historical transaction time of the current transaction, the transaction location and the historical transaction location of the current transaction, the transaction device identifier and the historical transaction device identifier respectively comprises:
calculating the time difference value between the transaction time of the current transaction and each historical transaction time, and taking the minimum time difference value as the deviation value between the transaction time of the current transaction and the historical transaction time;
calculating the distance between the transaction place of the current transaction and each historical transaction place, and taking the minimum distance as the deviation value of the transaction place of the current transaction and the historical transaction place;
judging whether a historical trading equipment identifier consistent with the trading equipment identifier of the current trading exists or not;
if the historical trading equipment identification consistent with the trading equipment identification of the current trading exists, taking a first preset numerical value as a deviation value of the trading equipment identification of the current trading and the historical trading equipment identification;
if the historical trading equipment identification consistent with the trading equipment identification of the current trading does not exist, taking a second preset numerical value as a deviation value of the trading equipment identification of the current trading and the historical trading equipment identification; wherein the first preset value is smaller than the second preset value.
4. The method according to claim 1, wherein after determining that the final risk value is not less than a preset threshold at the beginning of the year, further comprising:
sending the transaction data of the current transaction to a client of a transaction manager;
receiving an auditing result fed back by the client of the transaction manager;
if the auditing result indicates that the current transaction is a high-risk transaction, executing the closing of the current transaction;
and if the auditing result indicates that the current transaction is a low-risk transaction, executing the payment request responding to the current transaction.
5. An apparatus for online payments, comprising:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring transaction data of the current transaction, customer information corresponding to a payment account of the current transaction and historical transaction data of the payment account of the current transaction when receiving a payment request of the current transaction;
the first input unit is used for inputting the transaction data and the customer information into a first neural network model trained in advance, and calculating a risk pre-evaluation value of the current transaction through the first neural network model;
the second input unit is used for inputting the risk estimated value of the current transaction and the historical transaction data into a pre-trained second neural network model, and calculating through the second neural network model to obtain a final risk value of the current transaction;
the first judgment unit is used for judging whether the final risk value is smaller than a preset threshold value or not;
the identity authentication unit is used for performing identity information authentication on a target user initiating the current transaction and asking questions to the target user when the first judgment unit judges that the final risk value is smaller than a preset threshold value;
the payment unit is used for responding to the payment request of the current transaction when the target user passes identity information verification and the received question answer of the target user is correct;
and the closing unit is used for closing the current transaction when the first judging unit judges that the final risk value is not less than a preset threshold value.
6. The apparatus of claim 5, further comprising:
the second acquisition unit is used for acquiring the transaction time, the transaction place and the transaction equipment identifier of the current transaction;
the deviation value calculating unit is used for respectively calculating deviation values of the transaction time and the historical transaction time of the current transaction, the transaction place and the historical transaction place of the current transaction, and the transaction equipment identifier and the historical transaction equipment identifier of the current transaction;
the second judging unit is used for judging whether the sum of the deviation values is larger than a preset deviation value or not; when the second judgment unit judges that the sum of all deviation values is larger than a preset deviation value, the first input unit inputs the transaction data and the customer information into a first pre-trained neural network model, and a risk pre-estimated value of the current transaction is obtained through calculation of the first neural network model.
7. The apparatus of claim 6, wherein the offset value calculating unit comprises:
the first calculation unit is used for calculating the time difference value between the transaction time of the current transaction and each historical transaction time, and taking the minimum time difference value as the deviation value between the transaction time of the current transaction and the historical transaction time;
the second calculation unit is used for calculating the distance between the transaction place of the current transaction and each historical transaction place, and taking the minimum distance as the deviation value of the transaction place of the current transaction and the historical transaction place;
a third judging unit, configured to judge whether there is a historical transaction device identifier that is consistent with the transaction device identifier of the current transaction;
the first assignment unit is used for taking a first preset numerical value as a deviation value of the transaction equipment identifier of the current transaction and the historical transaction equipment identifier when the third judgment unit judges that the historical transaction equipment identifier consistent with the transaction equipment identifier of the current transaction exists;
the second assignment unit is used for taking a second preset numerical value as a deviation value of the transaction equipment identifier of the current transaction and the historical transaction equipment identifier when the third judgment unit judges that the historical transaction equipment identifier consistent with the transaction equipment identifier of the current transaction does not exist; wherein the first preset value is smaller than the second preset value.
8. The apparatus of claim 5, further comprising:
the sending unit is used for sending the transaction data of the current transaction to a client of a transaction manager;
the receiving unit is used for receiving an auditing result fed back by the client of the transaction manager; if the auditing result indicates that the current transaction is a high-risk transaction, the closing unit executes the closing of the current transaction; and if the auditing result indicates that the current transaction is a low-risk transaction, the payment unit executes the payment request responding to the current transaction.
9. An electronic device, comprising:
a memory and a processor;
wherein the memory is used for storing programs;
the processor is adapted to execute the program, which when executed is particularly adapted to implement a method of on-line payment as claimed in any one of claims 1 to 4.
10. A computer storage medium storing a computer program which, when executed, is adapted to implement a method of on-line payment as claimed in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010898825.5A CN112016929B (en) | 2020-08-31 | 2020-08-31 | Method and device for online payment, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010898825.5A CN112016929B (en) | 2020-08-31 | 2020-08-31 | Method and device for online payment, electronic equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112016929A true CN112016929A (en) | 2020-12-01 |
| CN112016929B CN112016929B (en) | 2023-08-04 |
Family
ID=73503279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010898825.5A Active CN112016929B (en) | 2020-08-31 | 2020-08-31 | Method and device for online payment, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112016929B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112954379A (en) * | 2021-02-09 | 2021-06-11 | 中国工商银行股份有限公司 | Live broadcast control method and device |
| CN113095834A (en) * | 2021-04-12 | 2021-07-09 | 中国工商银行股份有限公司 | Risk transaction identification method, device and system |
| CN113743945A (en) * | 2021-09-03 | 2021-12-03 | 深圳刷宝科技有限公司 | Method and device for switching payment verification modes based on risks |
| CN115021937A (en) * | 2022-06-21 | 2022-09-06 | 中国银行股份有限公司 | User identity authentication method, system, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080294540A1 (en) * | 2007-05-25 | 2008-11-27 | Celka Christopher J | System and method for automated detection of never-pay data sets |
| CN108876105A (en) * | 2018-05-10 | 2018-11-23 | 易联支付有限公司 | A kind of transaction risk control method and device |
| CN111539711A (en) * | 2020-04-24 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Security business transaction method and device and electronic equipment |
-
2020
- 2020-08-31 CN CN202010898825.5A patent/CN112016929B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080294540A1 (en) * | 2007-05-25 | 2008-11-27 | Celka Christopher J | System and method for automated detection of never-pay data sets |
| CN108876105A (en) * | 2018-05-10 | 2018-11-23 | 易联支付有限公司 | A kind of transaction risk control method and device |
| CN111539711A (en) * | 2020-04-24 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Security business transaction method and device and electronic equipment |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112954379A (en) * | 2021-02-09 | 2021-06-11 | 中国工商银行股份有限公司 | Live broadcast control method and device |
| CN112954379B (en) * | 2021-02-09 | 2023-04-21 | 中国工商银行股份有限公司 | Live broadcast control method and device |
| CN113095834A (en) * | 2021-04-12 | 2021-07-09 | 中国工商银行股份有限公司 | Risk transaction identification method, device and system |
| CN113743945A (en) * | 2021-09-03 | 2021-12-03 | 深圳刷宝科技有限公司 | Method and device for switching payment verification modes based on risks |
| CN113743945B (en) * | 2021-09-03 | 2023-06-30 | 深圳刷宝科技有限公司 | Method and device for switching payment verification modes based on risks |
| CN115021937A (en) * | 2022-06-21 | 2022-09-06 | 中国银行股份有限公司 | User identity authentication method, system, electronic equipment and storage medium |
| CN115021937B (en) * | 2022-06-21 | 2024-02-09 | 中国银行股份有限公司 | User identity authentication method, system, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112016929B (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112016929B (en) | Method and device for online payment, electronic equipment and computer storage medium | |
| Dorronsoro et al. | Neural fraud detection in credit card operations | |
| US8116731B2 (en) | System and method for mobile identity protection of a user of multiple computer applications, networks or devices | |
| AU2018201140B2 (en) | System and method for candidate profile screening | |
| US9652772B1 (en) | Systems and methods for fraud detection | |
| CN109857766B (en) | User information verification method and device, computer equipment and computer storage medium | |
| CN110570188A (en) | Method and system for processing transaction requests | |
| US20230267470A1 (en) | Flexible authentication | |
| CN111899100A (en) | Service control method, device and equipment and computer storage medium | |
| CN112016931A (en) | Online transaction method and device, electronic equipment and computer storage medium | |
| US20190295086A1 (en) | Quantifying device risk through association | |
| CN112016930A (en) | Detection method of transaction security, related device and computer storage medium | |
| CN112330355A (en) | Consumption ticket transaction data processing method, device, equipment and storage medium | |
| CN111489175A (en) | Online identity authentication method, device, system and storage medium | |
| CN107871213B (en) | Transaction behavior evaluation method, device, server and storage medium | |
| CN109271415B (en) | Data processing method and device for credit investigation database | |
| CN115392916A (en) | Abnormal consumption control method and device, electronic equipment and storage medium | |
| CN115439030A (en) | Capital and current information management system based on big data analysis | |
| US20230259757A1 (en) | Tiered input structures for machine learning models | |
| CN115907953A (en) | Vehicle lending scheme recommendation method and device, electronic equipment and computer storage medium | |
| CN113298641A (en) | Integrity degree cognition method and device | |
| CN113191875A (en) | Credit granting method and device for new user, electronic equipment and storage medium | |
| CN110648048A (en) | Applet signing event processing method, device, server and readable storage medium | |
| CN115713339B (en) | Data quantum computing management and control method, device, equipment and computer medium | |
| JP7176157B1 (en) | LEARNING MODEL CREATION SYSTEM, LEARNING MODEL CREATION METHOD AND PROGRAM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |